© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 210048
    Prev
    Next
    INDEX
    Explanations

    typically stored, emotions, stories, adapt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    한다는
    0.44
    痛み
    0.43
     melhorar
    0.42
    闱
    0.42
    ዚህ
    0.42
     ಹೊಂದಿದೆ
    0.42
     diminishes
    0.41
    傃
    0.41
    ಿಸುವ
    0.41
    heiros
    0.41
    POSITIVE LOGITS
     ]
    0.43
     defense
    0.41
     approximately
    0.40
     ]]
    0.40
     canc
    0.38
     خال
    0.38
     surrounded
    0.38
     )}
    0.38
    hab
    0.37
     storage
    0.37
    Activations Density 0.002%

    No Known Activations